Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3190 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5698. Min Range: -3.5698

Max Act: 3.5698. Min Act: -0.0000

Data Index: 1083880 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 3.5698. Min Range: -3.5698

Max Act: 3.3951. Min Act: -0.0000

Data Index: 1052989 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 3.5698. Min Range: -3.5698

Max Act: 3.1754. Min Act: -0.0000

Data Index: 432697 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 3.5698. Min Range: -3.5698

Max Act: 3.2987. Min Act: -0.0000

Data Index: 1073231 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 3.5698. Min Range: -3.5698

Max Act: 3.2669. Min Act: -0.0000

Data Index: 271517 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 3.5698. Min Range: -3.5698

Max Act: 3.1537. Min Act: -0.0000

Data Index: 623920 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 3.5698. Min Range: -3.5698

Max Act: 3.0434. Min Act: -0.0000

Data Index: 1214830 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 3.5698. Min Range: -3.5698

Max Act: 2.8924. Min Act: -0.0000

Data Index: 131962 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 3.5698. Min Range: -3.5698

Max Act: 2.8710. Min Act: -0.0000

Data Index: 776034 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 3.5698. Min Range: -3.5698

Max Act: 2.8412. Min Act: -0.0000

Data Index: 712074 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 3.5698. Min Range: -3.5698

Max Act: 2.9656. Min Act: -0.0000

Data Index: 167594 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 3.5698. Min Range: -3.5698

Max Act: 2.7897. Min Act: -0.0000

Data Index: 335434 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 3.5698. Min Range: -3.5698

Max Act: 2.8974. Min Act: -0.0000

Data Index: 1128977 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 3.5698. Min Range: -3.5698

Max Act: 2.7230. Min Act: -0.0000

Data Index: 115534 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 3.5698. Min Range: -3.5698

Max Act: 2.5629. Min Act: -0.0000

Data Index: 8901 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 3.5698. Min Range: -3.5698

Max Act: 2.7023. Min Act: -0.0000

Data Index: 246178 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 3.5698. Min Range: -3.5698

Max Act: 2.6622. Min Act: -0.0000

Data Index: 1071295 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 3.5698. Min Range: -3.5698

Max Act: 2.4838. Min Act: -0.0000

Data Index: 329778 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 3.5698. Min Range: -3.5698

Max Act: 2.5893. Min Act: -0.0000

Data Index: 354278 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 3.5698. Min Range: -3.5698

Max Act: 2.5585. Min Act: -0.0000

Data Index: 1004620 (C4 (Web Text))

Max Activating Token Index: 113